© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96347
    Prev
    Next
    INDEX
    Explanations

    emoticons or special characters indicating strong emotions or reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ingham
    -0.07
    oling
    -0.07
    itles
    -0.07
    ега
    -0.06
     Cunning
    -0.06
    aucoup
    -0.06
    име
    -0.06
    _TRACE
    -0.06
     bÃłi
    -0.06
    oro
    -0.06
    POSITIVE LOGITS
    CDATA
    0.06
     Beck
    0.06
    .ManyToMany
    0.06
    .Elapsed
    0.06
    (Me
    0.06
    Äįen
    0.06
     Nun
    0.06
     Bou
    0.06
     Liv
    0.06
    anvas
    0.06
    Activations Density 0.000%

    No Known Activations